{"total":107,"rows":[{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901,"area":"lr"},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886,"area":"lr"},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841,"area":null},{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832,"area":"synth"},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652,"area":"lr"},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596,"area":"lr"},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558,"area":null},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531,"area":"agents"},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429,"area":"agents"},{"id":"2303.17491","title":"Language Models can Solve Computer Tasks","created":"2023-03-30","cited_by_count":372,"area":null},{"id":"2210.01240","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","created":"2022-10-03","cited_by_count":337,"area":"lr"},{"id":"2306.03314","title":"Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents","created":"2023-06-05","cited_by_count":333,"area":"agents"},{"id":"2212.14024","title":"Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP","created":"2022-12-28","cited_by_count":318,"area":"rag"},{"id":"2406.11695","title":"Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs","created":"2024-06-17","cited_by_count":291,"area":null},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252,"area":"lr"},{"id":"2209.00840","title":"FOLIO: Natural Language Reasoning with First-Order Logic","created":"2022-09-02","cited_by_count":235,"area":"lr"},{"id":"2311.05772","title":"ADaPT: As-Needed Decomposition and Planning with Language Models","created":"2023-11-08","cited_by_count":177,"area":"lr"},{"id":"2310.15164","title":"LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers","created":"2023-10-23","cited_by_count":168,"area":"lr"},{"id":"2403.04642","title":"Teaching Large Language Models to Reason with Reinforcement Learning","created":"2024-03-07","cited_by_count":160,"area":"lr"},{"id":"2310.02304","title":"Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation","created":"2023-10-03","cited_by_count":148,"area":"synth"},{"id":"2302.14838","title":"EvoPrompting: Language Models for Code-Level Neural Architecture Search","created":"2023-02-28","cited_by_count":131,"area":null},{"id":"2303.16755","title":"Training Language Models with Language Feedback at Scale","created":"2023-03-28","cited_by_count":128,"area":"alignment"},{"id":"2312.04474","title":"Chain of Code: Reasoning with a Language Model-Augmented Code Emulator","created":"2023-12-07","cited_by_count":123,"area":"lr"},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2306.12672","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","created":"2023-06-22","cited_by_count":119,"area":"wm"},{"id":"2310.01089","title":"GraphText: Graph Reasoning in Text Space","created":"2023-10-02","cited_by_count":111,"area":"lr"},{"id":"2212.06094","title":"Prompting Is Programming: A Query Language for Large Language Models","created":"2022-12-12","cited_by_count":110,"area":null},{"id":"2310.15123","title":"Branch-Solve-Merge Improves Large Language Model Evaluation and Generation","created":"2023-10-23","cited_by_count":106,"area":null},{"id":"2305.08844","title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs","created":"2023-05-15","cited_by_count":105,"area":null},{"id":"2304.03843","title":"Why think step by step? Reasoning emerges from the locality of experience","created":"2023-04-07","cited_by_count":103,"area":"lr"},{"id":"2306.00937","title":"STEVE-1: A Generative Model for Text-to-Behavior in Minecraft","created":"2023-06-01","cited_by_count":97,"area":null},{"id":"2310.04363","title":"Amortizing intractable inference in large language models","created":"2023-10-06","cited_by_count":97,"area":null},{"id":"2404.17546","title":"Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo","created":"2024-04-26","cited_by_count":90,"area":"alignment"},{"id":"2304.13007","title":"Answering Questions by Meta-Reasoning over Multiple Chains of Thought","created":"2023-04-25","cited_by_count":87,"area":"lr"},{"id":"2208.11663","title":"PEER: A Collaborative Language Model","created":"2022-08-24","cited_by_count":86,"area":null},{"id":"2306.03081","title":"Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs","created":"2023-06-05","cited_by_count":80,"area":null},{"id":"2305.16960","title":"Training Socially Aligned Language Models on Simulated Social Interactions","created":"2023-05-26","cited_by_count":78,"area":"alignment"},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2403.11322","title":"StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows","created":"2024-03-17","cited_by_count":65,"area":null},{"id":"2212.10561","title":"Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions","created":"2022-12-20","cited_by_count":64,"area":"lr"},{"id":"2305.19165","title":"Strategic Reasoning with Language Models","created":"2023-05-30","cited_by_count":64,"area":"lr"},{"id":"2305.19234","title":"Grammar Prompting for Domain-Specific Language Generation with Large Language Models","created":"2023-05-30","cited_by_count":58,"area":null},{"id":"2301.04589","title":"Memory Augmented Large Language Models are Computationally Universal","created":"2023-01-10","cited_by_count":47,"area":null},{"id":"2308.10855","title":"LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzles","created":"2023-08-21","cited_by_count":41,"area":"lr"},{"id":"2503.17523","title":"Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models","created":"2025-03-21","cited_by_count":37,"area":"lr"},{"id":"2310.09139","title":"The Consensus Game: Language Model Generation via Equilibrium Search","created":"2023-10-13","cited_by_count":36,"area":null},{"id":"2310.16035","title":"What's Left? Concept Grounding with Logic-Enhanced Foundation Models","created":"2023-10-24","cited_by_count":33,"area":"lr"},{"id":"2306.12509","title":"Joint Prompt Optimization of Stacked LLMs using Variational Inference","created":"2023-06-21","cited_by_count":32,"area":null},{"id":"2312.12009","title":"Active Preference Inference using Language Models and Probabilistic Reasoning","created":"2023-12-19","cited_by_count":29,"area":"lr"},{"id":"2402.06025","title":"Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning","created":"2024-02-08","cited_by_count":24,"area":"lr"},{"id":"2210.01293","title":"ThinkSum: Probabilistic reasoning over sets using large language models","created":"2022-10-04","cited_by_count":23,"area":"lr"},{"id":"2210.02498","title":"Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model","created":"2022-10-05","cited_by_count":20,"area":null},{"id":"2306.16207","title":"Inferring the Goals of Communicating Agents from Actions and Instructions","created":"2023-06-28","cited_by_count":17,"area":"agents"},{"id":"2310.14420","title":"Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst Design","created":"2023-10-22","cited_by_count":17,"area":"lr"},{"id":"2406.05213","title":"On Subjective Uncertainty Quantification and Calibration in Natural Language Generation","created":"2024-06-07","cited_by_count":16,"area":null},{"id":"2410.22480","title":"Scaling LLM Inference with Optimized Sample Compute Allocation","created":"2024-10-29","cited_by_count":16,"area":"lr"},{"id":"2301.01751","title":"Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes","created":"2023-01-04","cited_by_count":15,"area":"lr"},{"id":"2209.08141","title":"Psychologically-informed chain-of-thought prompts for metaphor understanding in large language models","created":"2022-09-16","cited_by_count":14,"area":"lr"},{"id":"2210.02506","title":"Large Language Models are Pretty Good Zero-Shot Video Game Bug Detectors","created":"2022-10-05","cited_by_count":14,"area":null},{"id":"2506.09669","title":"Query-Level Uncertainty in Large Language Models","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2212.06295","title":"Despite \"super-human\" performance, current LLMs are unsuited for decisions about ethics and safety","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2305.18498","title":"ANPL: Towards Natural Programming with Interactive Decomposition","created":"2023-05-29","cited_by_count":13,"area":null},{"id":"2303.15714","title":"Explicit Planning Helps Language Models in Logical Reasoning","created":"2023-03-28","cited_by_count":12,"area":"lr"},{"id":"2402.19471","title":"Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Sampling","created":"2024-02-29","cited_by_count":12,"area":null},{"id":"2501.11877","title":"From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning","created":"2025-01-21","cited_by_count":12,"area":"lr"},{"id":"2302.02801","title":"LaMPP: Language Models as Probabilistic Priors for Perception and Action","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2305.05364","title":"Large Language Model Programs","created":"2023-05-09","cited_by_count":11,"area":null},{"id":"2309.11197","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","created":"2023-09-20","cited_by_count":10,"area":null},{"id":"2310.09536","title":"CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering","created":"2023-10-14","cited_by_count":10,"area":"rag"},{"id":"2502.19335","title":"Gatekeeper: Improving Model Cascades Through Confidence Tuning","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2503.13505","title":"Ensemble Learning for Large Language Models in Text and Code Generation: A Survey","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2511.06190","title":"Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning","created":"2025-11-09","cited_by_count":9,"area":"lr"},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2211.03277","title":"Complex Reading Comprehension Through Question Decomposition","created":"2022-11-07","cited_by_count":7,"area":null},{"id":"2212.08607","title":"MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation","created":"2022-12-16","cited_by_count":7,"area":"lr"},{"id":"2308.11807","title":"Towards an On-device Agent for Text Rewriting","created":"2023-08-22","cited_by_count":7,"area":"agents"},{"id":"2310.04680","title":"The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning","created":"2023-10-07","cited_by_count":7,"area":null},{"id":"2504.12988","title":"Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2407.06146","title":"Using Grammar Masking to Ensure Syntactic Validity in LLM-based Modeling Tasks","created":"2024-07-08","cited_by_count":6,"area":null},{"id":"2307.00660","title":"Minimum Levels of Interpretability for Artificial Moral Agents","created":"2023-07-02","cited_by_count":5,"area":null},{"id":"2408.08624","title":"RealMedQA: A pilot biomedical question answering dataset containing realistic clinical questions","created":"2024-08-16","cited_by_count":5,"area":null},{"id":"2409.05367","title":"STRICTA: Structured Reasoning in Critical Text Assessment for Peer Review and Beyond","created":"2024-09-09","cited_by_count":5,"area":"lr"},{"id":"2412.17696","title":"Understanding the Logic of Direct Preference Alignment through Logic","created":"2024-12-23","cited_by_count":5,"area":"alignment"},{"id":"2210.11265","title":"Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers","created":"2022-10-20","cited_by_count":3,"area":"lr"},{"id":"2310.01441","title":"UPAR: A Kantian-Inspired Prompting Framework for Enhancing Large Language Model Capabilities","created":"2023-09-30","cited_by_count":3,"area":null},{"id":"2311.04954","title":"Prompt Sketching for Large Language Models","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2506.15733","title":"$\\texttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts","created":"2025-06-15","cited_by_count":3,"area":"lr"},{"id":"2502.18573","title":"FactReasoner: A Probabilistic Approach to Long-Form Factuality Assessment for Large Language Models","created":"2025-02-25","cited_by_count":2,"area":"lr"},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2603.07101","title":"Grounding Machine Creativity in Game Design Knowledge Representations: Empirical Probing of LLM-Based Executable Synthesis of Goal Playable Patterns under Structural Constraints","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2604.17290","title":"Probabilistic Programs of Thought","created":"2026-04-19","cited_by_count":1,"area":"lr"},{"id":"2604.23072","title":"Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis","created":"2026-04-24","cited_by_count":1,"area":"lr"},{"id":"2605.19557","title":"Density-Ratio Losses for Post-Hoc Learning to Defer","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2607.04542","title":"Auto: The AGI Compiler","created":"2026-07-05","cited_by_count":1,"area":"agents"},{"id":"2608.13571","title":"Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems","created":"2026-07-02","cited_by_count":1,"area":"agents"},{"id":"2407.18945","title":"CogNarr Ecosystem: Facilitating Group Cognition at Scale","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2512.23049","title":"Accelerating Language Model Workflows with Prompt Choreography","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2601.02365","title":"FUSE : Failure-aware Usage of Subagent Evidence for MultiModal Search and Recommendation","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2604.14531","title":"TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification","created":"2026-04-16","cited_by_count":0,"area":null}],"next_cursor":"100"}